A Feed-Forward Neural Network Approach for Energy-Based Acoustic Source Localization

Journal of Sensor and Actuator Networks

Slavisa Tomic¹  SérgioD. Correia¹  Marko Beko² 

[1] COPELABS, Universidade Lusófona de Humanidades e Tecnologias, Campo Grande 376, 1749-024 Lisboa, Portugal;Instituto de Telecominicações, Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal;

关键词: acoustic localization;    artificial intelligence;    artificial neural networks;    deep feed-forward networks;    deep learning;    embedded computing;   

DOI  :  10.3390/jsan10020029

来源: DOAJ

【 摘 要 】

The localization of an acoustic source has attracted much attention in the scientific community, having been applied in several different real-life applications. At the same time, the use of neural networks in the acoustic source localization problem is not common; hence, this work aims to show their potential use for this field of application. As such, the present work proposes a deep feed-forward neural network for solving the acoustic source localization problem based on energy measurements. Several network typologies are trained with ideal noise-free conditions, which simplifies the usual heavy training process where a low mean squared error is obtained. The networks are implemented, simulated, and compared with conventional algorithms, namely, deterministic and metaheuristic methods, and our results indicate improved performance when noise is added to the measurements. Therefore, the current developed scheme opens up a new horizon for energy-based acoustic localization, a field where machine learning algorithms have not been applied in the past.

【 授权许可】

Unknown